Skip to content
Permalink
Browse files

MDEV-19580 Unrelated JOINs corrupt usage of 'WHERE function() IN (sub…

…query)'

Handling of top level conjuncts in WHERE whose used_tables() contained
RAND_TABLE_BIT in the function make_join_select() was incorrect.
As a result if such a conjunct referred to fields non of which belonged
to the last joined table  it was pushed twice. (This could be seen
for a test case from subselect.test whose output was changed after this
patch had been applied. In 10.1 when running EXPLAIN FORMAT=JSON for
the query from this test case we clearly see that one of the conjuncts
is pushed twice.) This fact by itself was not good. Besides, if such a
conjunct was pushed to a table that was the result of materialization
of a semi-join the query could return a wrong result set. In particular
we could watch it for queries with semi-join subqueries whose left parts
used stored functions without "deterministic' specifier.
  • Loading branch information...
igorbabaev committed Jun 9, 2019
1 parent 6660c07 commit 6db2ebbb2a63994ef2b43d42a11dbacb8b55c207
@@ -6939,7 +6939,7 @@ WHERE SLEEP(0.1) OR c < 'p' OR b = ( SELECT MIN(b) FROM t2 );
id select_type table type possible_keys key key_len ref rows Extra
1 PRIMARY t1 system NULL NULL NULL NULL 1
1 PRIMARY t2 ALL b NULL NULL NULL 2 Using where
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using where; Using index
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using index
3 SUBQUERY NULL NULL NULL NULL NULL NULL NULL Select tables optimized away
set @tmp_mdev410=@@global.userstat;
set global userstat=on;
@@ -2453,6 +2453,95 @@ SELECT 1 FROM t1 where t1.id IN (SELECT v1.i1 from v1);
1
drop table t1,t2;
drop view v1;
#
# MDEV-19580: function invocation in the left part of IN subquery
#
create table t1 (id int, a varchar(50), b int);
insert into t1 values
(1,'mrs',2), (2,'joe',2), (3,'paul',1), (4,'art',1);
create table t2 (id int, a varchar(50), x int);
insert into t2 values
(1,'grand',1),(2,'average',1),(3,'serf',0);
create table t3 (d1 date, d2 date, t1_id int, t2_id int );
insert into t3 values
('1972-01-01','1988-12-31',3,1), ('1972-01-01','1988-12-31',4,1),
('1972-01-01','1988-12-31',1,2), ('1972-01-01','1988-12-31',2,3);
create table t4 ( id int, a varchar(50) );
insert into t4 values
(1,'songwriter'),(2,'song character');
create function f1(who int, dt date) returns int
deterministic
begin
declare result int;
select t2_id into result from t3 where dt>=d1 and dt<=d2 and t1_id=who;
return result;
end$$
create function f2(who int, dt date) returns int
begin
declare result int;
select t2_id into result from t3 where dt>=d1 and dt<=d2 and t1_id=who;
return result;
end$$
# Deterministic function in left part of IN subquery: semi-join is OK
select * from t1
left join t4 on t1.b = t4.id
where f1(t1.id, '1980-01-01') in (select id from t2 where x=1);
id a b id a
3 paul 1 1 songwriter
4 art 1 1 songwriter
1 mrs 2 2 song character
explain extended select * from t1
left join t4 on t1.b = t4.id
where f1(t1.id, '1980-01-01') in (select id from t2 where x=1);
id select_type table type possible_keys key key_len ref rows filtered Extra
1 PRIMARY t1 ALL NULL NULL NULL NULL 4 100.00
1 PRIMARY <subquery2> eq_ref distinct_key distinct_key 4 func 1 100.00 Using where
1 PRIMARY t4 ALL NULL NULL NULL NULL 2 100.00 Using where; Using join buffer (flat, BNL join)
2 MATERIALIZED t2 ALL NULL NULL NULL NULL 3 100.00 Using where
Warnings:
Note 1003 select `test`.`t1`.`id` AS `id`,`test`.`t1`.`a` AS `a`,`test`.`t1`.`b` AS `b`,`test`.`t4`.`id` AS `id`,`test`.`t4`.`a` AS `a` from `test`.`t1` semi join (`test`.`t2`) left join `test`.`t4` on((`test`.`t4`.`id` = `test`.`t1`.`b`)) where ((`test`.`t2`.`x` = 1) and (`f1`(`test`.`t1`.`id`,'1980-01-01') = `test`.`t2`.`id`))
# Non-deterministic function in left part of IN subq: semi-join is OK
select * from t1
left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id a b id a
3 paul 1 1 songwriter
4 art 1 1 songwriter
1 mrs 2 2 song character
explain extended select * from t1
left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id select_type table type possible_keys key key_len ref rows filtered Extra
1 PRIMARY t1 ALL NULL NULL NULL NULL 4 100.00
1 PRIMARY <subquery2> eq_ref distinct_key distinct_key 4 func 1 100.00 Using where
1 PRIMARY t4 ALL NULL NULL NULL NULL 2 100.00 Using where; Using join buffer (flat, BNL join)
2 MATERIALIZED t2 ALL NULL NULL NULL NULL 3 100.00 Using where
Warnings:
Note 1003 select `test`.`t1`.`id` AS `id`,`test`.`t1`.`a` AS `a`,`test`.`t1`.`b` AS `b`,`test`.`t4`.`id` AS `id`,`test`.`t4`.`a` AS `a` from `test`.`t1` semi join (`test`.`t2`) left join `test`.`t4` on((`test`.`t4`.`id` = `test`.`t1`.`b`)) where ((`test`.`t2`.`x` = 1) and (`f2`(`test`.`t1`.`id`,'1980-01-01') = `test`.`t2`.`id`))
select t1.*, t4.*,
(select max(t4.id) from t4 where t4.id=t1.b and sleep(0) = 0) as s
from t1 left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id a b id a s
3 paul 1 1 songwriter 1
4 art 1 1 songwriter 1
1 mrs 2 2 song character 2
explain extended select t1.*, t4.*,
(select max(t4.id) from t4 where t4.id=t1.b and sleep(0) = 0) as s
from t1 left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id select_type table type possible_keys key key_len ref rows filtered Extra
1 PRIMARY t1 ALL NULL NULL NULL NULL 4 100.00
1 PRIMARY <subquery3> eq_ref distinct_key distinct_key 4 func 1 100.00 Using where
1 PRIMARY t4 ALL NULL NULL NULL NULL 2 100.00 Using where; Using join buffer (flat, BNL join)
3 MATERIALIZED t2 ALL NULL NULL NULL NULL 3 100.00 Using where
2 DEPENDENT SUBQUERY t4 ALL NULL NULL NULL NULL 2 100.00 Using where
Warnings:
Note 1276 Field or reference 'test.t1.b' of SELECT #2 was resolved in SELECT #1
Note 1003 select `test`.`t1`.`id` AS `id`,`test`.`t1`.`a` AS `a`,`test`.`t1`.`b` AS `b`,`test`.`t4`.`id` AS `id`,`test`.`t4`.`a` AS `a`,(select max(`test`.`t4`.`id`) from `test`.`t4` where ((`test`.`t4`.`id` = `test`.`t1`.`b`) and (sleep(0) = 0))) AS `s` from `test`.`t1` semi join (`test`.`t2`) left join `test`.`t4` on((`test`.`t4`.`id` = `test`.`t1`.`b`)) where ((`test`.`t2`.`x` = 1) and (`f2`(`test`.`t1`.`id`,'1980-01-01') = `test`.`t2`.`id`))
drop function f1;
drop function f2;
drop table t1,t2,t3,t4;
# End of 5.5 tests
set @subselect_mat_test_optimizer_switch_value=null;
set @@optimizer_switch='materialization=on,in_to_exists=off,semijoin=off';
@@ -6937,7 +6937,7 @@ WHERE SLEEP(0.1) OR c < 'p' OR b = ( SELECT MIN(b) FROM t2 );
id select_type table type possible_keys key key_len ref rows Extra
1 PRIMARY t1 system NULL NULL NULL NULL 1
1 PRIMARY t2 ALL b NULL NULL NULL 2 Using where
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using where; Using index
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using index
3 SUBQUERY NULL NULL NULL NULL NULL NULL NULL Select tables optimized away
set @tmp_mdev410=@@global.userstat;
set global userstat=on;
@@ -6934,7 +6934,7 @@ WHERE SLEEP(0.1) OR c < 'p' OR b = ( SELECT MIN(b) FROM t2 );
id select_type table type possible_keys key key_len ref rows Extra
1 PRIMARY t1 system NULL NULL NULL NULL 1
1 PRIMARY t2 ALL b NULL NULL NULL 2 Using where
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using where; Using index
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using index
3 SUBQUERY NULL NULL NULL NULL NULL NULL NULL Select tables optimized away
set @tmp_mdev410=@@global.userstat;
set global userstat=on;
@@ -6945,7 +6945,7 @@ WHERE SLEEP(0.1) OR c < 'p' OR b = ( SELECT MIN(b) FROM t2 );
id select_type table type possible_keys key key_len ref rows Extra
1 PRIMARY t1 system NULL NULL NULL NULL 1
1 PRIMARY t2 ALL b NULL NULL NULL 2 Using where
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using where; Using index
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using index
3 SUBQUERY NULL NULL NULL NULL NULL NULL NULL Select tables optimized away
set @tmp_mdev410=@@global.userstat;
set global userstat=on;
@@ -6934,7 +6934,7 @@ WHERE SLEEP(0.1) OR c < 'p' OR b = ( SELECT MIN(b) FROM t2 );
id select_type table type possible_keys key key_len ref rows Extra
1 PRIMARY t1 system NULL NULL NULL NULL 1
1 PRIMARY t2 ALL b NULL NULL NULL 2 Using where
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using where; Using index
1 PRIMARY t3 ref d d 5 test.t2.b 2 Using index
3 SUBQUERY NULL NULL NULL NULL NULL NULL NULL Select tables optimized away
set @tmp_mdev410=@@global.userstat;
set global userstat=on;
@@ -2493,4 +2493,93 @@ SELECT 1 FROM t1 where t1.id IN (SELECT v1.i1 from v1);
1
drop table t1,t2;
drop view v1;
#
# MDEV-19580: function invocation in the left part of IN subquery
#
create table t1 (id int, a varchar(50), b int);
insert into t1 values
(1,'mrs',2), (2,'joe',2), (3,'paul',1), (4,'art',1);
create table t2 (id int, a varchar(50), x int);
insert into t2 values
(1,'grand',1),(2,'average',1),(3,'serf',0);
create table t3 (d1 date, d2 date, t1_id int, t2_id int );
insert into t3 values
('1972-01-01','1988-12-31',3,1), ('1972-01-01','1988-12-31',4,1),
('1972-01-01','1988-12-31',1,2), ('1972-01-01','1988-12-31',2,3);
create table t4 ( id int, a varchar(50) );
insert into t4 values
(1,'songwriter'),(2,'song character');
create function f1(who int, dt date) returns int
deterministic
begin
declare result int;
select t2_id into result from t3 where dt>=d1 and dt<=d2 and t1_id=who;
return result;
end$$
create function f2(who int, dt date) returns int
begin
declare result int;
select t2_id into result from t3 where dt>=d1 and dt<=d2 and t1_id=who;
return result;
end$$
# Deterministic function in left part of IN subquery: semi-join is OK
select * from t1
left join t4 on t1.b = t4.id
where f1(t1.id, '1980-01-01') in (select id from t2 where x=1);
id a b id a
3 paul 1 1 songwriter
4 art 1 1 songwriter
1 mrs 2 2 song character
explain extended select * from t1
left join t4 on t1.b = t4.id
where f1(t1.id, '1980-01-01') in (select id from t2 where x=1);
id select_type table type possible_keys key key_len ref rows filtered Extra
1 PRIMARY t1 ALL NULL NULL NULL NULL 4 100.00
1 PRIMARY <subquery2> eq_ref distinct_key distinct_key 4 func 1 100.00 Using where
1 PRIMARY t4 ALL NULL NULL NULL NULL 2 100.00 Using where; Using join buffer (flat, BNL join)
2 MATERIALIZED t2 ALL NULL NULL NULL NULL 3 100.00 Using where
Warnings:
Note 1003 select `test`.`t1`.`id` AS `id`,`test`.`t1`.`a` AS `a`,`test`.`t1`.`b` AS `b`,`test`.`t4`.`id` AS `id`,`test`.`t4`.`a` AS `a` from `test`.`t1` semi join (`test`.`t2`) left join `test`.`t4` on((`test`.`t4`.`id` = `test`.`t1`.`b`)) where ((`test`.`t2`.`x` = 1) and (`f1`(`test`.`t1`.`id`,'1980-01-01') = `test`.`t2`.`id`))
# Non-deterministic function in left part of IN subq: semi-join is OK
select * from t1
left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id a b id a
3 paul 1 1 songwriter
4 art 1 1 songwriter
1 mrs 2 2 song character
explain extended select * from t1
left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id select_type table type possible_keys key key_len ref rows filtered Extra
1 PRIMARY t1 ALL NULL NULL NULL NULL 4 100.00
1 PRIMARY <subquery2> eq_ref distinct_key distinct_key 4 func 1 100.00 Using where
1 PRIMARY t4 ALL NULL NULL NULL NULL 2 100.00 Using where; Using join buffer (flat, BNL join)
2 MATERIALIZED t2 ALL NULL NULL NULL NULL 3 100.00 Using where
Warnings:
Note 1003 select `test`.`t1`.`id` AS `id`,`test`.`t1`.`a` AS `a`,`test`.`t1`.`b` AS `b`,`test`.`t4`.`id` AS `id`,`test`.`t4`.`a` AS `a` from `test`.`t1` semi join (`test`.`t2`) left join `test`.`t4` on((`test`.`t4`.`id` = `test`.`t1`.`b`)) where ((`test`.`t2`.`x` = 1) and (`f2`(`test`.`t1`.`id`,'1980-01-01') = `test`.`t2`.`id`))
select t1.*, t4.*,
(select max(t4.id) from t4 where t4.id=t1.b and sleep(0) = 0) as s
from t1 left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id a b id a s
3 paul 1 1 songwriter 1
4 art 1 1 songwriter 1
1 mrs 2 2 song character 2
explain extended select t1.*, t4.*,
(select max(t4.id) from t4 where t4.id=t1.b and sleep(0) = 0) as s
from t1 left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);
id select_type table type possible_keys key key_len ref rows filtered Extra
1 PRIMARY t1 ALL NULL NULL NULL NULL 4 100.00
1 PRIMARY <subquery3> eq_ref distinct_key distinct_key 4 func 1 100.00 Using where
1 PRIMARY t4 ALL NULL NULL NULL NULL 2 100.00 Using where; Using join buffer (flat, BNL join)
3 MATERIALIZED t2 ALL NULL NULL NULL NULL 3 100.00 Using where
2 DEPENDENT SUBQUERY t4 ALL NULL NULL NULL NULL 2 100.00 Using where
Warnings:
Note 1276 Field or reference 'test.t1.b' of SELECT #2 was resolved in SELECT #1
Note 1003 select `test`.`t1`.`id` AS `id`,`test`.`t1`.`a` AS `a`,`test`.`t1`.`b` AS `b`,`test`.`t4`.`id` AS `id`,`test`.`t4`.`a` AS `a`,(select max(`test`.`t4`.`id`) from `test`.`t4` where ((`test`.`t4`.`id` = `test`.`t1`.`b`) and (sleep(0) = 0))) AS `s` from `test`.`t1` semi join (`test`.`t2`) left join `test`.`t4` on((`test`.`t4`.`id` = `test`.`t1`.`b`)) where ((`test`.`t2`.`x` = 1) and (`f2`(`test`.`t1`.`id`,'1980-01-01') = `test`.`t2`.`id`))
drop function f1;
drop function f2;
drop table t1,t2,t3,t4;
# End of 5.5 tests
@@ -2230,4 +2230,79 @@ explain SELECT 1 FROM t1 where t1.id IN (SELECT v1.i1 from v1);
SELECT 1 FROM t1 where t1.id IN (SELECT v1.i1 from v1);
drop table t1,t2;
drop view v1;


--echo #
--echo # MDEV-19580: function invocation in the left part of IN subquery
--echo #

create table t1 (id int, a varchar(50), b int);
insert into t1 values
(1,'mrs',2), (2,'joe',2), (3,'paul',1), (4,'art',1);

create table t2 (id int, a varchar(50), x int);
insert into t2 values
(1,'grand',1),(2,'average',1),(3,'serf',0);

create table t3 (d1 date, d2 date, t1_id int, t2_id int );
insert into t3 values
('1972-01-01','1988-12-31',3,1), ('1972-01-01','1988-12-31',4,1),
('1972-01-01','1988-12-31',1,2), ('1972-01-01','1988-12-31',2,3);

create table t4 ( id int, a varchar(50) );
insert into t4 values
(1,'songwriter'),(2,'song character');

delimiter $$;

create function f1(who int, dt date) returns int
deterministic
begin
declare result int;
select t2_id into result from t3 where dt>=d1 and dt<=d2 and t1_id=who;
return result;
end$$

create function f2(who int, dt date) returns int
begin
declare result int;
select t2_id into result from t3 where dt>=d1 and dt<=d2 and t1_id=who;
return result;
end$$

delimiter ;$$

--echo # Deterministic function in left part of IN subquery: semi-join is OK

let $q1=
select * from t1
left join t4 on t1.b = t4.id
where f1(t1.id, '1980-01-01') in (select id from t2 where x=1);

eval $q1;
eval explain extended $q1;

--echo # Non-deterministic function in left part of IN subq: semi-join is OK

let $q2=
select * from t1
left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);

eval $q2;
eval explain extended $q2;

let $q3=
select t1.*, t4.*,
(select max(t4.id) from t4 where t4.id=t1.b and sleep(0) = 0) as s
from t1 left join t4 on t1.b = t4.id
where f2(t1.id, '1980-01-01') in (select id from t2 where x=1);

eval $q3;
eval explain extended $q3;

drop function f1;
drop function f2;
drop table t1,t2,t3,t4;

--echo # End of 5.5 tests

0 comments on commit 6db2ebb

Please sign in to comment.
You can’t perform that action at this time.